AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Bi-Level Doubly Variational Learning for Energy-Based Latent Variable Models

Ge Kan, Jinhu Lü, Tian Wang, Baochang Zhang, Aichun Zhu, Lei Huang, Guodong Guo, Hichem Snoussi

CVPR 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Amortized and online variational inference · 4 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use the complete decoupled EBLVM with symmetric KL, rather than symmetric KL alone in a coupled EBLVM (ablation)BiDVL · CIFAR-10FID: 32.10 -> 20.75Improved
set the basic importance ratio to 0.05 rather than 0.01 (ablation)BiDVL · CIFAR-10FID: 22.62 -> 20.75Improved
increase the basic importance ratio from 0.05 to 0.5 or 1.0 (ablation)BiDVL · CIFAR-10FID: 20.75 -> 26.82; 29.72Hurt
offset the opposite gradient terms (ablation)BiDVL · CIFAR-10FID: 21.54 -> 20.75Improved
offset the opposite gradient terms (ablation)BiDVL · CIFAR-10RMSE: 0.170 -> 0.168Improved
remove the opposite terms from the algorithm (ablation)BiDVL · CIFAR-10FID: 20.75 -> 20.24Improved
remove the opposite terms from the algorithm (ablation)BiDVL · CIFAR-10RMSE: 0.168 -> 0.175Hurt
remove the opposite terms from the algorithm (ablation)BiDVL · CIFAR-10 training; SVHN and CelebA OODAUROC: 0.81 AUROC on SVHN; 0.75 AUROC on CelebAMixed
use the sigmoid estimate for the importance-ratio bias term instead of ignoring the bias term (ablation)BiDVL · image generationFIDHurt
use a ResNet-based architecture (ablation)BiDVL · CIFAR-10FID: 20.75 -> 16.37Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy